Security audit
Security checks for vulnerabilities and agentic risk
This skill is a cloud-infrastructure helper, but it presents production apply/destroy commands without clear safeguards or confirmation guidance.
Review this skill before installing. It is not evidence of malware, but users should only enable it where infrastructure-changing commands require explicit approval, dry-run or plan review, and strong separation from production credentials unless intentionally operating production resources.
The trigger keywords are generic terms like 'cloud', 'automation', and 'management' that are likely to match ordinary user conversation and invoke this skill unexpectedly. Because the skill exposes both read and exec capabilities and is oriented toward infrastructure operations, accidental activation could lead to unintended command suggestions or execution paths in a sensitive environment.
The skill documents destructive actions such as './cloud.sh destroy prod' and frames infrastructure provisioning/management as routine without any warning, confirmation requirement, or guardrail around production environments. In the context of an exec-enabled infrastructure skill, this materially increases the chance of accidental destructive operations causing outages, data loss, or irrecoverable resource deletion.
A substantial portion of the skill metadata and description is written in Chinese, while the rest of the file is in English, and there is no statement that users can choose their preferred language. This can violate language or locale policy when a specific language is imposed without opt-in or justification.
No suspicious patterns detected.
